← back
Security Track Intro — Randall Degges, Snyk
Takeaway
Secure-by-default development and controlled agent execution are prerequisites for confidently scaling AI-assisted software.
Summary
- AI-generated code can contain vulnerabilities just as human-written code can, so security remains part of the software development lifecycle.
- Autonomous production agents add a harder problem: constraining actions that could harm users or businesses while operating without direct supervision.
- The introduction announces the World's Fair security track, bringing together presenters from NVIDIA, Anthropic, Keycard, and Snyk to address these barriers.
ai-securitysecure-developmentconference-intro
Original description
Building software with AI almost feels like a cheat code: you ship what you were working on and watch it spark joy in real users. The catch, and the reason Randall Degges is opening the World's Fair's first Security Track, is that three things still stand in the way of doing that at scale. AI writes insecure code just like humans do, autonomous agents in production can go off the rails while you sleep, and access to frontier models keeps getting pulled out from under you for what amounts to geopolitics. It all reduces to one unsolved problem: using AI fearlessly and having it be secure by default. Speaker info: https://x.com/rdegges https://github.com/rdegges https://rdegges.com